Outside: a private streak app that listens to your walk with open-source AI
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Outside is a small, private Android app that gets me off the screen and into the world. I tap "I'm outside", put the phone in my pocket, and walk. While I'm out, the app listens to the sounds around me and writes them into a journal, so a walk becomes "Birds, water, wind" instead of just "20…
This is a recount of an Android application called "Outside" that was developed as part of the Hacktoberfest Open-Source AI Challenge Week 1. The app encourages users to spend more time outdoors by listening to ambient sounds and converting them into a journal. The user simply taps "I'm outside," puts the phone in their pocket, and walks.
As they walk, the app records ambient sounds and categorizes them into eight friendly categories such as birds, water, wind, traffic, etc. The app uses YAMNet, an open-weight model developed by Google, to recognize 521 sound classes. The app works offline, meaning it doesn't require any internet connection and stores all the data locally on the device.
The sound journal is saved as plain text, which users can export at any time. The application is deliberately designed to be private and not social, with no account, feed, or photo posting features. The app is also battery-efficient, as it only listens to sounds when the screen is on and the app is open. The developer tested the app by playing various sounds near the microphone and made adjustments to the sound categorization based on the model's raw guesses.
The app was built using HTML, CSS, and JavaScript, wrapped as an Android app with Capacitor. The developer highlighted the importance of open innovation and the benefits of using open-source models like YAMNet, which allows for customization and privacy.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
